can it run
No. 16GB of memory can't hold the 25GB working set this model needs. A smaller quant or a bigger machine is required.
weights 20GB + KV cache 1GB at 4k context vs ~16GB usable → no. 21.0 GB vs 16 GB usable — does not fit
computed roofline: 732 GB/s × 0.17–0.38 efficiency window / 20.0GB (Q4_K_M) — bands, never points.
| model file | 20GB (GGUF Q4_K_M) |
| minimum memory | 25GB working set |
| this machine | 16GB HBM2, 732 GB/s |
| params | distill 32B |
| license | mit |
| price | $135 |
easy run: ollama pull deepseek-r1:32b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ Mac mini M5 Pro (64GB) — cheapest machine that runs it ($1669)
→ every model the Tesla P100 (16GB, used) can run — full list
→ tesla-v100-16gb — the next step up from this machine's GPU